| Abolfazl Hashemi

May 2026: 4 New papers out, 2 on distributional RL, one on:
- Asynchronous TD Learning for Distributional RL:
- Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation
- Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise
- Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
- A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
May 2026: Our paper below is accepted to 2026 International Conference on Machine Learning (ICML):
- Variance-Reduced Zeroth-Order Langevin Dynamics for Non-Log-Concave Black-Box Sampling and Inverse Problems
May 2026: Our papers below are accepted to 2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW):
- Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models
- Multimodal Abnormality Classifier Using Anatomy-Guided Connection for 3D Medical Images
January–April 2026: New papers out:
- Lower Bounds and Proximally Anchored SGD for Non-Convex Minimization Under Unbounded Variance
- RAMPAGE: RAndomized Mid-Point for debiAsed Gradient Extrapolation
- Joint MDPs and Reinforcement Learning in Coupled-Dynamics Environments
- First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints
- FedSGM: A Unified Framework for Constraint Aware, Bidirectionally Compressed, Multi-Step Federated Optimization
February 2026: Our paper below is accepted to Transactions on Machine Learning Research (TMLR):
- Learning to Localize Leakage of Cryptographic Sensitive Variables
January 2026: Our paper below is accepted to 2026 International Conference on Learning Representations (ICLR):
- Memorization Through the Lens of Sample Gradients
December 2025: Our paper below is accepted to Transactions on Machine Learning Research (TMLR):
- Characterizing Evolution in Expectation-Maximization Estimates for Overspecified Mixed Linear Regression
November 2025: New paper out:
- Structural Properties, Cycloid Trajectories and Non-Asymptotic Guarantees of EM Algorithm for Mixed Linear Regression
October 2025: New paper out:
- Beyond Convexity: Proximal-Perturbed Lagrangian Methods for Efficient Functional Constrained Optimization
September 2025: Our paper below is accepted to Conference on Neural Information Processing Systems (NeurIPS):
- Principled Long-Tailed Generative Modeling via Diffusion Models
August 2025: New paper out:
- Characterizing Evolution in Expectation-Maximization Estimates for Overspecified Mixed Linear Regression
July 2025: New paper out:
- Strong Antithetic Variates: Theory and Applications
June 2025: Our paper below is accepted to Elsevier Energy:
- Towards Memorization Estimation: Fast, Formal and Free
May 2025: New paper out:
- Optimization via First-Order Switching Methods: Skew-Symmetric Dynamics and Optimistic Discretization
May 2025: Our paper below is accepted to 2025 International Conference on Machine Learning (ICML):
- Towards Memorization Estimation: Fast, Formal and Free
April 2025: Our paper below is accepted to 2025 IEEE International Symposium on Information Theory (ISIT):
- Strong Antithetic Variance Reduction Inequalities
March 2025: Two new papers out:
- Building Machine Learning Challenges for Anomaly Detection in Science
- Learning to Localize Leakage of Cryptographic Sensitive Variables
January 2025: Our paper below is accepted to 2025 International Conference on Learning Representations (ICLR):
- Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
November 2024: Our paper below is accepted to IEEE Transactions on Signal Processing:
- Localized Distributional Robustness in Submodular Multi-Task Subset Selection
October 2024: New paper out:
- Equitable Federated Learning with Activation Clustering
October 2024: Our paper below is accepted to IEEE Transactions on Automatic Control:
- A Unified Model for Large-Scale Inexact Fixed-Point Iteration: A Stochastic Optimization Perspective
September 2024: Our paper below is accepted to IEEE Transactions on Automatic Control:
- Accelerated Distributed Stochastic Non-Convex Optimization over Time-Varying Directed Networks
August 2024: New paper out:
- Submodular Maximization Approaches for Equitable Client Selection in Federated Learning
August 2024: Our paper below is accepted to Automatica:
- Randomized Greedy Methods for Weak Submodular Sensor Selection with Robustness Considerations
July 2024: Our paper below is accepted to IEEE Conference on Decision and Control:
- Equitable Client Selection in Federated Learning via Truncated Submodular Maximization
May 2024: Our two papers below are accepted to ICML 2024:
- Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression
- Unveiling Privacy, Memorization, and Input Curvature Links
April 2024: Our paper below is accepted to UAI 2024 as oral presentation:
- Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes
April 2024: Four new papers out:
- Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis
- Randomized Greedy Methods for Weak Submodular Sensor Selection with Robustness Considerations
- Localized Distributional Robustness in Submodular Multi-Task Subset Selection
- AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
March 2024: New paper out:
- FedNMUT – Federated Noisy Model Update Tracking Convergence Analysis
February 2024: New paper out:
- Unveiling Privacy, Memorization, and Input Curvature Links
January 2024: Our paper on MRI phase synthesis with diffusion models is accepted to 32nd Annual Meeting of ISMRM
December 2023: I am serving as an Area Chair for ICML 2024
November 2023: Our paper on Deep Learning-based Image Reconstruction is accpeted to 27th Annual Scientific Sessions of SCMR
October 2023: Excited to start NSF CPS Medium: Learning through the Air: Cross-Layer UAV Orchestration for Online Federated Optimization
October 2023: Our paper “No-Regret Learning in Dynamic Stackelberg Games” is accepted to IEEE Transactions on Automatic Control.
October 2023: I am serving as an Area Chair for AISTATS 2024
September 2023: Our paper Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data is accepted to NeurIPS 2023
August 2023: Our two papers on High probability Results for Federated Learning and Robust Sensor Selection are accepted to 2023 Allerton Conference on Communication, Control, and Computing
July 2023: Our three papers on High probability Results for Sensor Selection, Improved Results for Noisy Federated Learning, and Online Reinforcement Learning are accepted to 2023 Asilomar Conference on Signals, Systems, and Computers
June 2023: Our journal paper “On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing” is accepted to IEEE Control Systems Letters.
June 2023: Our journal papers “Improved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise” and “Communication-Efficient Zeroth-Order Distributed Online Optimization: Algorithm, Theory, and Applications” are accepted to IEEE Access.
March 2023: I am giving an invited talk on “Theory-guided Methods for Private Federated Learning” at SIAM CSE
February 2023: Our papers “Communication-Constrained Exchange of Zeroth-Order Information with Application to Collaborative Target Tracking” and “Accelerated Decentralized Stochastic Non-Convex Optimization over Directed Networks” are accepted to ICASSP 2023
February 2023: I am giving an invited talk on “No-Regret Learning in Dynamic Stackelberg Games” at ITA 2023.
January 2023: Our paper “Randomized Greedy Algorithms for Sensor Selection in Large-Scale Satellite Constellations” is accepted to ACC 2023
December 2022: I am co-organizing four invited sessions on Distributed Learning and Decision Making at ITA 2023
November 2022: Our paper on Deep Learning for Low-latency Image Reconstruction is accpeted to 31st Annual Meeting of ISMRM
October 2022: I am serving as an Area Chair for AISTATS 2023
September 2022: Invited talk at SIAM MDS on Generalization Bounds for Sparse Random Feature Expansions. (Slides)
August 2022: Generalization Bounds for Sparse Random Feature Expansions is accepted to Applied and Computational Harmonic Analysis.
July 2022: On the Benefits of Progressively Increasing Sampling Sizes in Stochastic Greedy Weak Submodular Maximization is accepted to IEEE Transactions on Signal Processing.
May 2022: Faster Non-Convex Federated Learning via Global and Local Momentum is accepted to The 2022 Conference on Uncertainty in Artificial Intelligence (UAI).
April 2022: Invited talk at FLOW on Privacy Preserving Federated Learning. (Slides)
April 2022:I will be teaching a new graduate course on Optimization for Deep Learning in Fall 2022.
March 2022: Learning in Markov Decision Processes with Varying Rewards: High Probability Regret Bounds under Bandit Feedback and Unknown Horizon is conditionally accepted to IEEE Transactions on Automatic Control.
February 2022: New paper out:
- No-Regret Learning in Dynamic Stackelberg Games
February 2022: Towards Accelerated Greedy Sampling and Reconstruction of Bandlimited Graph Signals is accepted to The Elsevier Signal Processing.
January 2022: Robust Training in High Dimensions via Block Coordinate Geometric Median Descent is accepted to The 2022 International Conference on Artificial Intelligence and Statistics (AISTATS).
December 2021: On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Federated Learning is accepted to IEEE Transactions on Parallel and Distributed System.
November 2021: Communication-Efficient Variance-Reduced Decentralized Stochastic Optimization over Time-Varying Directed Graphs is accepted to IEEE Transactions on Automatic Control.
October 2021: Invited talk at CERIAS on Robustness and Security and in Adversarial Environments (Slides)
September 2021: Invited talks at Purdue CS department and ICON on Collaborative Learning (Slides)
August 2021: Started as an Assistant Professor of ECE at Purdue!
June 2021: Three new papers out:
- Robust Generative Adversarial Imitation Learning via Local Lipschitzness
- Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
- DP-NormFedAvg: Normalizing Client Updates for Privacy-Preserving Federated Learning
May 2021: “No-Regret Learning with High-Probability in Adversarial Markov Decision Processes is accepted to UAI 2021
March 2021: Our paper Function Approximation via Sparse Random Features is trending on DeepAI
March 2021: New paper out:
- Generalization Bounds for Sparse Random Feature Expansions
January 2021: Three papers are accepted to ICASSP 2021
January 2021: One paper is accepted to ACC 2021
January 2021: New paper out:
- Communication-Efficient Variance-Reduced Decentralized Stochastic Optimization over Time-Varying Directed Graphs
December 2020: New paper out:
- Faster Non-Convex Federated Learning via Global and Local Momentum
November 2020: New paper out:
- On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized Optimization
September 2020: Started my Postdoc at Oden Institute!
August 2020: I successfully defended my dissertation!